Multi-view Human Pose and Shape Estimation Using Learnable Volumetric Aggregation.
Soyong ShinEni HalilajPublished in: CoRR (2020)
Keyphrases
- multi view
- human pose
- pose estimation
- three dimensional
- human body
- d objects
- action recognition
- body parts
- single view
- depth images
- depth map
- multiple views
- human motion
- range data
- photometric stereo
- semi supervised
- human actions
- articulated objects
- view synthesis
- range images
- surface reconstruction
- pedestrian detection
- learning algorithm
- shape from shading
- d scene
- object recognition
- depth information
- video sequences
- image segmentation
- computer vision
- machine learning